{"total":79,"rows":[{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66,"area":"offlinerl"},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43,"area":"offlinerl"},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2302.03201","title":"Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR","created":"2023-02-07","cited_by_count":32,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2306.12755","title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning","created":"2023-06-22","cited_by_count":27,"area":"offlinerl"},{"id":"2210.05650","title":"Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2022-10-11","cited_by_count":26,"area":null},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2207.10295","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","created":"2022-07-21","cited_by_count":22,"area":"offlinerl"},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2302.09456","title":"Distributional Offline Policy Evaluation with Predictive Error Guarantees","created":"2023-02-19","cited_by_count":20,"area":"diffusion"},{"id":"2112.07701","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","created":"2021-12-14","cited_by_count":16,"area":null},{"id":"2210.14051","title":"Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"id":"2510.07650","title":"Value Flows","created":"2025-10-09","cited_by_count":15,"area":"deeprl"},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2212.01105","title":"Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery","created":"2022-12-02","cited_by_count":12,"area":"offlinerl"},{"id":"2206.06841","title":"Robust Reinforcement Learning with Distributional Risk-averse formulation","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2402.08421","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","created":"2024-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2211.15034","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","created":"2022-11-28","cited_by_count":9,"area":null},{"id":"2202.00769","title":"Distributional Reinforcement Learning with Regularized Wasserstein Loss","created":"2022-02-01","cited_by_count":8,"area":null},{"id":"2306.14479","title":"Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization","created":"2023-06-26","cited_by_count":8,"area":"offlinerl"},{"id":"2309.06239","title":"Risk-Aware Reinforcement Learning through Optimal Transport Theory","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2307.07091","title":"Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning","created":"2023-07-13","cited_by_count":6,"area":"offlinerl"},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2503.05238","title":"Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2110.03155","title":"Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning","created":"2021-10-07","cited_by_count":5,"area":null},{"id":"2302.11694","title":"Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control","created":"2023-02-22","cited_by_count":5,"area":null},{"id":"2308.13011","title":"Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2209.14513","title":"How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?","created":"2022-09-29","cited_by_count":4,"area":null},{"id":"2305.00677","title":"Robustified Learning for Online Optimization with Memory Costs","created":"2023-05-01","cited_by_count":4,"area":null},{"id":"2305.13804","title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","created":"2023-05-23","cited_by_count":4,"area":"offlinerl"},{"id":"2502.18955","title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset","created":"2025-02-26","cited_by_count":4,"area":"offlinerl"},{"id":"2310.20098","title":"Robust Learning for Smoothed Online Convex Optimization with Feedback Delay","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2405.18729","title":"Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning","created":"2024-05-29","cited_by_count":3,"area":"diffusion"},{"id":"2210.10469","title":"Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation","created":"2022-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2307.00547","title":"Is Risk-Sensitive Reinforcement Learning Properly Resolved?","created":"2023-07-02","cited_by_count":2,"area":null},{"id":"2403.17646","title":"Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning","created":"2024-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2507.03900","title":"Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning","created":"2025-07-05","cited_by_count":2,"area":"offlinerl"},{"id":"2511.02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","created":"2025-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","cited_by_count":2,"area":"offlinerl"},{"id":"2605.08253","title":"Path-Coupled Bellman Flows for Distributional Reinforcement Learning","created":"2026-05-07","cited_by_count":2,"area":"offlinerl"},{"id":"2205.07150","title":"Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systems","created":"2022-05-14","cited_by_count":1,"area":null},{"id":"2306.06329","title":"HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach","created":"2023-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2307.11704","title":"JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2407.06317","title":"Enhanced Safety in Autonomous Driving: Integrating Latent State Diffusion Model for End-to-End Navigation","created":"2024-07-08","cited_by_count":1,"area":"driving"},{"id":"2605.08515","title":"Quantile-Coupled Flow Matching for Distributional Reinforcement Learning","created":"2026-05-08","cited_by_count":1,"area":"diffusion"},{"id":"2606.27766","title":"RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance","created":"2026-06-26","cited_by_count":1,"area":"offlinerl"},{"id":"2606.29820","title":"Dual-Flow Reinforcement Learning with State-Aware Exploration","created":"2026-06-29","cited_by_count":1,"area":"deeprl"},{"id":"2111.08817","title":"Compressive Features in Offline Reinforcement Learning for Recommender Systems","created":"2021-11-16","cited_by_count":0,"area":"offlinerl"},{"id":"2205.08369","title":"Applications of Reinforcement Learning in Deregulated Power Market: A Comprehensive Review","created":"2022-05-07","cited_by_count":0,"area":null},{"id":"2404.12639","title":"Data-Incremental Continual Offline Reinforcement Learning","created":"2024-04-19","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07541","title":"CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2408.12446","title":"EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning","created":"2024-08-22","cited_by_count":0,"area":"deeprl"},{"id":"2501.04421","title":"Risk-averse policies for natural gas futures trading using distributional reinforcement learning","created":"2025-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2509.10303","title":"Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions","created":"2025-09-12","cited_by_count":0,"area":"offlinerl"},{"id":"2510.02695","title":"RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2512.01987","title":"Forecasting in Offline Reinforcement Learning for Non-stationary Environments","created":"2025-12-01","cited_by_count":0,"area":"offlinerl"},{"id":"2601.00737","title":"Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertainty","created":"2026-01-02","cited_by_count":0,"area":"deeprl"},{"id":"2601.01917","title":"Distorted Distributional Policy Evaluation for Offline Reinforcement Learning","created":"2026-01-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.05890","title":"DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.13061","title":"Native Extrapolation Awareness in Flow-Based Conditional Generation","created":"2026-02-13","cited_by_count":0,"area":"diffusion"},{"id":"2605.14779","title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning","created":"2026-05-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.15620","title":"Pessimistic Risk-Aware Policy Learning in Contextual Bandits","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2608.03108","title":"Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL","created":"2026-08-04","cited_by_count":0,"area":"offlinerl"},{"id":"2609.32828","title":"Retimed Bellman Flows: Escaping the Impossible Triangle of Velocity Bootstrapping","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2610.17788","title":"Posterior-Averaged Bellman Flow Matching for Distributional Critics","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}